digitado

This blog post discusses the details of what finetuning is, why it’s needed, and how we can finetune an LLM model with practical examples. The fine-tuning is what brings life to the LLM model. It’s a technique to make models adapt to a specific task, such as coding, writing poems or songs, classifying objects in an image, etc. A typical lifecycle of LLM training is depicted below. In the pretraining model, it only learns to predict the next token, […]

Ver mais

L2 distance told me two audio fingerprints were similar. They weren’t. The problem wasn’t my model. It was the metric. If you have not read my last blog on vector index, it will help you understand why I am doing what I am doing. Access this story for free here The Problem With L2 OmniPulse revolves around WST fingerprints. They aren’t a single point in space. They are the distribution of energy across wavelet scales and time. Two fingerprints can have similar […]

Ver mais

Training large language models on long sequences has a well-known problem: attention is expensive. The scaled dot-product attention (SDPA) at the core of every transformer scales quadratically Θ(N²) in both compute and memory with sequence length N. FlashAttention addressed this through IO-aware tiling that avoids materializing the full N×N attention matrix in high-bandwidth memory, reducing the memory footprint significantly, but the underlying Θ(N²) compute scaling remains. Researchers at Nous Research have introduced a new method called Lighthouse Attention […]

Ver mais

A hybrid A* + Deep Reinforcement Learning system in Unity, an SR-71, 5 million training steps, and the architectural insight that made it work. When a fighter pilot flies a routine sortie, they don’t improvise — they follow the plan. When a missile lock alarm goes off, they don’t follow the plan — they improvise. Classical AI is great at the first thing. Reinforcement learning is great at the second. So why does almost everyone try to use one of them for both? That […]

Ver mais

My practical fixes for costly blind spots It was 11:47 PM on a Tuesday when Marcus, a senior engineer I used to work with, dropped me a Slack message. His company’s finance team had just asked him: “Can you explain this AWS/OpenAI charge? $48,200. This month.” The agent had been live for three weeks. It passed all their staging tests. Ninety‑two percent on their internal eval suite. The team had high‑fived the launch. Then Marcus opened the logs and started scrolling. […]

Ver mais

Running AI agents in a local script is straightforward. Running them reliably in production across teams, across restarts, with isolated environments per context is a different problem entirely. BerriAI, the company behind the LiteLLM AI Gateway, is now open-sourcing a purpose-built answer to that problem: the LiteLLM Agent Platform. The platform is described as a simple, self-hosted infrastructure platform for running multiple agents in production. What Problem Does it Solve? It helps to understand what happens when you […]

Ver mais